List your company

Hallucination Detection on SC-Vicuna (AUCPR)

91.1AUCPRSELFCHECKGPT
84.13285.94187.7589.559Jul 28, 2025

Evaluation results

MethodLinks
SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.0791.1
SELFCHECKGPTDetector=Gemma 3, Future context=true2025.0790.7
SCDetector=LLaMA 3.1, Future context=true2025.0790.3
SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.0790.2
SELFCHECKGPTDetector=Gemma 3, Future context=false2025.0789.3
DIRECTDetector=LLaMA 3.1, Future context=true2025.0789.2
SCDetector=Gemma 3, Future context=true2025.0788.5
SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.0788.5
DIRECTDetector=LLaMA 3.1, Future context=false2025.0788.4
SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.0788.4
SCDetector=LLaMA 3.1, Future context=false2025.0788.1
DIRECTDetector=Qwen 2.5, Future context=false2025.0787.9
DIRECTDetector=Qwen 2.5, Future context=true2025.0787.7
SCDetector=Gemma 3, Future context=false2025.0787.5
SCDetector=Qwen 2.5, Future context=true2025.0786
DIRECTDetector=Gemma 3, Future context=true2025.0784.9
DIRECTDetector=Gemma 3, Future context=false2025.0784.6
SCDetector=Qwen 2.5, Future context=false2025.0784.4